Newer posts are loading.
You are at the newest post.
Click here to check if anything new just came in.

November 15 2012

Software that keeps an eye on Grandma

Much of health care — particularly for the elderly — is about detecting change, and, as the mobile health movement would have it, computers are very good at that. Given enough sensors, software can model an individual’s behavior patterns and then figure out when things are out of the ordinary — when gait slows, posture stoops or bedtime moves earlier.

Technology already exists that lets users set parameters for households they’re monitoring. Systems are available that send an alert if someone leaves the house in the middle of the night or sleeps past a preset time. Those systems involve context-specific hardware (i.e., a bed-pressure sensor) and conscientious modeling (you have to know what time your grandmother usually wakes up).

The next step would be a generic system. One that, following simple setup, would learn the habits of the people it monitors and then detect the sorts of problems that beset elderly people living alone — falls, disorientation, and so forth — as well as more subtle changes in behavior that could signal other health problems.

A group of researchers from Austria and Turkey has developed just such a system, which they presented at the IEEE’s Industrial Electronics Society meeting in Montreal in October.*

Activity as surmised in different rooms by the researchers' machine-learning algorithmsActivity as surmised in different rooms by the researchers' machine-learning algorithms
Activity as surmised in different rooms by the researchers’ machine-learning algorithms. Source: “Activity Recognition Using a Hierarchical Model.”

In their approach, the researchers train a machine-learning algorithm with several days of routine household activity using door and motion sensors distributed through the living space. The sensors aren’t associated with any particular room at the outset: their software algorithmically determines the relative positions of the sensors, then classifies the rooms that they’re in based on activity patterns over the course of the day.

From there, it’s easy to train software with habits — when bedtime typically occurs, how long an occupant usually spends in the kitchen — though these are handled generically (you don’t need to label the bedroom as the bedroom in order for the algorithm to detect that something is amiss when the occupant spends too long there).

The result is somewhat more subtle in its understanding of how a household works and when something might be out of order: if movement in the bedroom between 7 and 8 A.M. is usually followed by the opening of the bedroom door, then the same movement pattern without the door opening might suggest that someone has fallen while getting out of bed.

The researchers found that, compared to activity manually labeled by test users, their system was accurate at 81% to 87% depending on the type of algorithm used (SVM, CVS, or Hierarchical).

Networks of devices can bring intelligence out of individual machines and into centralized software that can understand an environment in its totality. That’s a central part of the philosophy of the industrial Internet, in which networked machines feed data into sophisticated software that can solve complex optimization problems that take large systems into account.

Dietmar Bruckner, a professor at Vienna University of Technology and an author of the paper, says his software (known by the tortured acronym ATTEND — AdapTive scenario recogniTion for Emergency and Need Detection) is tailored to the home-monitoring case outlined in his paper, but it could eventually be generalized to other types of building-monitoring applications.

Asked about bringing the technology to market, Bruckner said his research was being discontinued under funding cutbacks at his university. That’s unfortunate given the technology industry’s interest in using machine intelligence to deliver better health care. Might this be an opportunity for a startup to pick up where Bruckner et al. leave off?

*Available for a fee from IEEE: C. Tirkaz, D. Bruckner, G. Yin, J. Haase, “Activity Recognition Using a Hierarchical Model,” Proceedings of the 38th Annual Conference of the IEEE Industrial Electronics Society, pp. 2802-2808, 2012.


This is a post in our industrial Internet series, an ongoing exploration of big machines and big data. The series is produced as part of a collaboration between O’Reilly and GE.

July 26 2012

Esther Dyson on health data, “preemptive healthcare” and the next big thing

If we look ahead to the next decade, it’s worth wondering whether the way we think about health and healthcare will have shifted. Will healthcare technology be a panacea? Will it drive even higher costs, creating a broader divide between digital haves and have-nots? Will opening health data empower patients or empower companies?

As ever, there will be good outcomes and bad outcomes, and not just in the medical sense. There’s a great deal of foment around the potential for mobile applications right now, from the FDA’s potential decision to regulate them to a reported high abandonment rate. There are also significant questions about privacy, patient empowerment and meaningful use of electronic healthcare records.

When I’ve talked to US CTO Todd Park or Dr. Farzad Mostashari they’ve been excited about the prospect for health data to fuel better dashboards and algorithms to give frontline caregivers access to critical information about people they’re looking after, providing critical insight at the point of contact.

Kathleen Sebelius, the U.S. Secretary for Health and Human Services, said at this year’s Health Datapalooza that venture capital investment in the Healthcare IT area is up 60 percent since 2009.

Given that context, I was more than a little curious to hear what Esther Dyson (@edyson) is thinking about when she looks at the intersection of healthcare, data and information technology.

"yes, but the sharks must love it!""yes, but the sharks must love it!"

[Photo Credit: Rick Smolan, via Esther Dyson]

Dyson, who started her career as a journalist, is now an angel investor and philanthropist. Dyson is a strong supporter of “preemptive healthcare” – and she’s putting her money where her interest lies, with her investments. She’ll be speaking at the StrataRX conference this October in San Francisco.

Our interview, which was lightly edited for content and clarity, follows.

How do you see healthcare changing?

Dyson: There’s multiple perspectives. The one I’ve got does not invalidate others, nor it is intended to any of trump the others, but it’s the one that I focus on — and that’s really “health” as opposed to “healthcare.”

If you maintain good health, you can avoid healthcare. That’s one of those great and unrealizable goals, but it’s realizable in part. Any healthcare you can avoid because you’re healthy is valuable.

What I’m mostly focused on is trying to change people’s behavior. You’ll get agreement from almost everybody that eating right, not smoking, getting exercise, avoiding too much stress, and sleeping a lot are good for your health.

The challenge is what makes people do those things, and that’s where there’s a real lack of data. So a lot of what I’m doing is investing on space. There’s evidence-based medicine. There’s also evidence-based prevention, and that’s even harder to validate.

Right now, a lot of people are doing a lot of different things. Many of them are collecting data, which over time, with luck, will prove that some of these things I’m going to talk about are valuable.

What does the landscape for healthcare products and services look like to you today?

Dyson: I see three markets.

There’s the traditional healthcare market, which is what people usually talk about. It’s drugs, clinics, hospitals, doctors, therapies, devices, insurance companies, data processors, or electronic health records.

Then there’s the market for bad health, which people don’t talk about a lot, at least not in those terms, but it’s huge. It’s the products and all of the advertising around everything from sugared soft drinks to cigarettes to recreational drugs to things that keep you from going to bed, going to sleep, keep you on the couch, and keep you immobile. I mentioned cigarettes and alcohol, I think. That’s a huge market. People are being encouraged to engage in unhealthy behaviors, whether it’s stuff that might be healthy in moderation or stuff that just isn’t healthy at all.

The new [third] market for health existed already as health clubs. What’s exciting is that there’s now an explicit market for things that are designed to change your behavior. Usually, they’re information and social-based. These are the quantified self – analytical tools, tools for sharing, tools for fostering collaboration or competition with people that behave in a healthy way. Most of those have very little data to back them up. It’s people think they make sense. The business models are still not too clear, because if I’m healthy, who’s going to pay for that? The chances are that if I’ll pay for it, I’m already kind of a health nut and don’t need it as much as someone who isn’t.

Pharma companies will pay for some such things, especially if they think that they can sell people drugs in conjunction with them. I’ll sell you a cholesterol lowering drug through a service that encourages you to exercise, for example. That’s a nice market. You go to the pre-diabetics and you sell them your statin. Various vendors of sports clubs and so forth will fund this. But over time, I expect you’re going to see employers realize the value of this, then finally long-term insurance companies and perhaps government. But it’s a market that operates mostly on faith at this point.

Speaking of faith, Rock Health shared data that around 80 percent of mobile health apps are being abandoned by consumers after two weeks. Thoughts?

Dyson: To me, that’s infant mortality. The challenge is to take the 20 percent and then make those persist. But yeah, you’re right, people try a lot of stuff and it turns out to be confusing and not well-designed, et cetera.

If you look ahead a decade, what are the big barriers for health data and mobile technology playing a beneficial role, as opposed to a more dystopian one?

Dyson: Well, the benign version is we’ve done a lot of experimentation. We’ve discovered that most apps have an 80 percent abandon rate, but the 20 percent that are persisting get better and better and better. So the 80 percent that are abandoned vanish and the marketplace and the vendors focus on the 20 percent. And we get broad adoption. You get onto the subway in New York and everybody’s thin and healthy.

Yeah, that’s not going to happen. But there’s some impact. Employers understand the value of this is. There’s a lot more to do than just these [mobile] apps. The employers start serving only healthy food in the cafeteria. Actually, one big sign is going to be what they serve for breakfast at Strata RX. I was at the Kauffman Life Sciences Entrepreneur Conference and they had muffins, bagels and cream cheese.

Carbohydrates and fat, in other words.

Dyson: And sugar-filled yogurts. That was the first day. They responded to somebody’s tweet [the second day] and it was better. But it’s not just the advertising. It’s the selection of stuff that you get when you go to these events or when you go to a hotel or you go to school or you go to your cafeteria at your office.

Defaults are tremendously important. That’s why I’m a big fan of what Bloomberg’s trying to do in New York. If you really want to buy two servings of soda, that’s fine, but the default serving should be one. I mean personally, I’d get rid of them entirely, but anyway. You know, make the defaults smaller dinner plates. All of this stuff really does have an impact.

Anyway, ten years from now, evidence has shown what works. What works is, in fact, working because people are doing it. A lot of this is social norms have changed. The early adopters have adopted, the late adopters are being carried along in the wake — just like there are still people who smoke, but it’s no longer the norm.

Do you have concerns or hopes for the risks and rewards of open health data releases?

Dyson: If we have a sensible healthcare system, the data will be helpful. Hospitals will say, “Oh my God, this guy’s at-risk, let’s prevent him getting sick.” Hospitals and the payers will know, “Gee, if we let this guy get sick, it’s going to cost us a lot more in the long run. And we actually have a business model that operates long-term rather than simply tries to minimize cost in the short-term.”

And insurance companies will say, “Gee, I’m paying for this guy. I better keep him healthy.” So the most important thing is for us to have a system that works long-term like that.

What role will personal data ownership play in the healthcare system of the future?

Dyson: Well, first we have to define what it is. I mean, from my point-of-view, you own your own data. On the other hand, if you want care, you’ve got to share it.

I think people are way too paranoid about their data. There will, inevitably, be data spills. We should try to avoid them, but we should also not encourage paranoia. If you have a rational economic system, privacy will be an issue, but financial security will not. Those two have gotten kind of mingled in people’s minds.

Yes, I may just want to keep it quiet that I have a sexually transmitted disease, but it’s not going to affect my ability to get treatment or to get insurance if I’ve got it. On the other hand, if I have to pay a little more for my diet soda or my hamburger because it’s being taxed, I don’t think that’s such a bad idea. Not that I want somebody recording how many hamburgers I eat, just tax them — but you don’t need to tax me personally: tax the hamburger.

What about the potential for the quantified self-movement to someday potentially reveal that hamburger consumption to insurers?

Dyson: You know, people are paranoid about insurers. They’re too busy. They’re not tracking the hamburgers you eat. They’re insuring populations. I mean seriously, you know? I went to get insurance and I told Aetna, “You can have my genetic profile.” And they said, “We wouldn’t know what to do with it.” I mean seriously, I’m not saying that’s entirely impossible ever in some kind of dystopia, but I really think people obsess too much about this kind of stuff.

How should — or could — startups in healthcare be differentiating themselves? What are the big problems that they could be working on solving?

Dyson: The whole social aspect. How do you design a game, a social interaction, that encourages people to react the way you want them to react? I mean, it’s just like what’s the difference between Facebook and Friendster. They both had the same potential user base. One was successful; one wasn’t. It’s the quality of the analytics, you show individuals about their behavior. It’s the narratives, the tools and the affordances that you give them for interacting with their friends. It’s like what makes one app different from another. They all use the same data in the end, but some of them are very, very different.

For what it’s worth, of the hundreds of companies that Rock Health or anybody else will tell you about, probably a third of them will disappear. One tenth will be highly successful and will acquire the remaining 57 percent.

What are the models that exist right now of the current landscape of healthcare startups that are really interesting to you? Why?

Dyson: I don’t think there’s a single one. There’s bunches of them occupying different places.

One area I really like is user-generated research and experiments. Obviously, 23andMe*. Deep analysis of your own data and the option to share it with other people and with researchers. User-generated data science research is really fascinating.

And then social affordance, like Kia’s Health Rally, where people interact with one and other. Omada Health (which I’m an investor in) is a Rock Health company which says we can’t do it all ourselves — there’s a designated counselor for a group. It’s right now focused on pre-diabetics.

I love that, partly because I think it’s going to be effective, and partly because I really like it as an employment model. I think our country is too focused on manufacturing and there’s a way to turn more people into health counselors. I mean, I’d take all of the laid off auto workers and turn them into gym teachers, and all the laid off engineers and turn them into data scientists or people developing health apps. Or something like that.

[*Dyson is an investor in 23andMe.]

What’s the biggest myth in the health data world? What’s the thing that drives you up the wall, so to speak?

Dyson: The biggest myth is that any single thing is the solution. The biggest need is for long-term thinking, which is everything from an individual thinking long-term about the impact of behavior to a financial institution thinking long-term and having the incentive to think long-term.

Individuals need to be influenced by psychology. Institutions, and the individuals in them, are employees that can be motivated or not. As an institution, they need financial incentives that are aligned with the long-term rather than the short-term.

That, again, goes back to having a vested interest in the health of people rather than in the cost of care.

Employers, to some extent, have that already. Your employer wants you to be healthy. They want you to show up for work, be cheerful, motivated and well rested. They get a benefit from you being healthy, far beyond simply avoiding the cost of your care.

Whereas the insurance companies, at this point, simply pass it through. If the insurance company is too effective, they actually have to lower their premiums, which is crazy. It’s really not insurance: it’s a cost-sharing and administration role that the insurance companies play. That’s something a lot of people don’t get. That needs to be fixed, one way or another.

May 25 2012

Top Stories: May 21-25, 2012

Here's a look at the top stories published across O'Reilly sites this week.

White House launches new digital government strategy
The nation's new strategy for digital government is built on data, shared services, citizen-centrism, and consistent methodologies for privacy and security.

Quantified me
Jim Stogdill is trying to walk the line between obsessive tracking and an open-ended approach to motivation.

A gaming revolution, minus the hype
"Playful Design" author John Ferrara discusses gaming's place in cultural transformation, and he offers five universal principles of good game design.

What do mHealth, eHealth and behavioral science mean for the future of healthcare?
Dr. Audie Atienza says we're just at the beginning of discovering how to best develop and utilize mobile technology to improve the health of individuals and the public.

Social reading should focus on common interests rather than friend status
In this TOC podcast, ReadSocial co-founder Travis Alber discusses her company's focus on building their platform without tying it to your social graph.


Velocity 2012: Web Operations & Performance — The smartest minds in web operations and performance are coming together for the Velocity Conference, being held June 25-27 in Santa Clara, Calif. Save 20% on registration with the code RADAR20.

White House photo: white house by dcJohn, on Flickr

May 21 2012

What do mHealth, eHealth and behavioral science mean for the future of healthcare?

We're living through one of the most dynamic periods in healthcare in our collective history. Earlier this year, Dr. Farzad Mostashari, the national coordinator of health IT, highlighted how the web, data and epatients are poised to revolutionize healthcare. The Internet is shaping healthcare in many ways, from the quantified self movement to participatory medicine, and even through the threat of a new "data divide" driven by unequal access to information, algorithmic and processing power.

Dr. Audie AtienzaInto this heady mix, add the mobile computing revolution, where smart devices rest in the pockets of hundreds of millions of citizens, collecting data and providing access to medical information. There's also the rapidly expanding universe of healthcare apps that promise to revolutionize how many services are created, distributed and delivered.

This month, I had the opportunity to discuss some of these trends with Dr. Audie Atienza (@AudieAtienza), a researcher who focuses on behavioral science and healthcare. Our interview, lightly edited for content and clarity, follows.

We first met when you were a senior health technology adviser at the U.S. Department of Health and Human Services (HHS). What do you do now?

Audie Atienza: Working with Todd Park at the Department of Health and Human Services (HHS) was a distinct privilege and an honor. I learned a great deal working at HHS with Todd. I am now at the new Science of Research and Technology Branch of the National Cancer Institute, National Institutes of Health.  My title is Behavioral Scientist and Health Scientist Administrator. In a typical week, I attend health-technology-related conferences and meetings, work with colleagues across HHS and the federal government on health-technology-related initiatives, discuss funding opportunities with extramural researchers, and engage in scientific research related to health technology and/or cancer control.

How well did your education prepare you for your work?

Audie Atienza: My undergraduate, graduate and post-doctoral education has provided me with the critical thinking skills and knowledge that is required of a health researcher. My interest in health technology actually started when I was a Fellow at Stanford University, where I was gathering data on cardiovascular disease risk factors using paper and pencil diaries.  Using paper and pencil measures seemed so inefficient. Study participants sometimes forgot to complete the diaries or had incomplete entries — and sometimes the handwriting was difficult to decipher.  So, my mentor, Dr. Abby King, and I collaborated with Dr. BJ Fogg (also at Stanford) and we "went digital" with the cardiovascular disease risk factor assessments. (We used "state of the art" PDAs at the time.)  This fortuitous collaboration and the "there has to be a better way to do this" idea launched me into the field of electronic and mobile health.

What does "eHealth" mean now?

Audie Atienza: After my postdoctoral fellowship at Stanford, I accepted a position at the National Cancer Institute (NCI), Health Promotion Research Branch.  The NCI offered me the opportunity to further explore the field of electronic health (or eHealth) on a national (U.S.) and international scale.  The term "eHealth" generally represents the use of electronic or digital information technology to assess and/or modify health behaviors, states and outcomes.

When I arrived at NCI, I was asked to bring the best and brightest behavioral researchers together to discuss how to assess health in "real-time."  A book was published based on this meeting: "The Science of Real-Time Data Capture Self-Reports in Health Research." Other national and international conferences followed, including the 2010 mHealth Summit, in which I was intimately involved.

How does behavioral science affect our capacity to understand the causes of cancer?

Audie Atienza: It is clear that behavioral factors contribute to cancer and many other diseases, like diabetes and heart disease.  For example, the link between smoking and cancer is well established. There is also a solid body of research that has linked obesity, physical inactivity, and poor diet to various cancers. The Centers for Disease Control (CDC) reports that 69% of U.S. adults are currently overweight or obese.[Data on adults: PDF and children: PDF]

Accurately measuring and changing these everyday health behaviors — including smoking, physical activity, what people eat — is not easy. This is where technology can be of great assistance. Through sensors, cell phones, GPS systems, social networking technology, and web-based technology, we may be able to better assess and hopefully improve these key health behaviors that contribute to cancer and other diseases.

We are, however, just at the beginning of discovering how to best develop and utilize technology to improve the health of individuals and the public.  There is much work to be done to determine what is effective and what isn't.

How do mobile devices figure into that work?

Audie Atienza: Mobile technology is everywhere. We are seeing more integrated devices, like smartphones with cameras, accelerometers, GPS, and all types of apps.  But it isn't about the technology — a phrase I have borrowed from Todd Park. It's really about addressing health issues and improving the health of individuals and the public.  If technology can facilitate this, then great. But using technology may not always be the best way to improve health and well-being.  This is a critical research question.

How is mobile technology being applied to specific health issues?

Audie Atienza: Mobile technology can be (and is being) applied to address many different health and disease issues: infection disease (AIDS/HIV, tuberculosis, influenza), chronic disease (heart disease, cancer, diabetes, arthritis, asthma), mental health (depression, stress, anxiety), child and maternal health (pregnancy, infant care, childhood obesity), gerontology (healthy living in place, falls prevention, caregiving), health promotion (e.g., exercise, diet, smoking cessation, cancer screening, sun safety), and health-provider-related issues (medication adherence, patient-provider communication, point-of-care diagnostics, vital signs monitoring).

Mobile technology cuts across the disease and health spectrum with great potential to address problems that have been previously difficult to solve.  It is difficult to say which mobile health technology is most important because they are all addressing distinct and critical issues.  Heart disease and cancer are the leading causes of death in the United States. Others may argue that infectious diseases and maternal/child health are the most critical issues to address globally. Still others may argue for tobacco control and reducing obesity (increasing physical activity and improving nutrition).  The National Institutes of Health (NIH) has 27 institutes and centers (ICs), each with a particular mission.  More than 20 of the 27 ICs are currently funding mobile technology-related research.

What do we need next in mHealth?

Audie Atienza: More research. We need to better understand what works and what does not. Researchers who have systematically reviewed smartphone health apps (e.g., smoking cessation, diabetes) have found that most are not based on established public health or clinical guidelines. Very few have actually assessed whether the apps are effective in changing health outcomes. With thousands of apps, sensors, and other mobile health tools currently available, it can be difficult for the user to know what is effective, useful, and (most importantly) safe.

How close are we to a real tricorder? (There's now an X Prize for that.)

Audie Atienza: I love science-fiction and "Star Trek"!  Certainly, mobile sensors and monitors currently exist that can accurately monitor physiological states and vital signs. And the technology is becoming increasingly integrated and more powerful.  But, to have an all-in-one mobile device that can assess and diagnose health and diseases as well as, if not better than, a clinical provider is a very tall order. If such a tool or prototype is developed, it will be science and research that will determine if the "tricorder" is effective or not.  Time will tell whether such a tool can be developed.  While I am all for reducing diagnostic errors, I personally would be hesitant to accept a diagnosis from only a mobile device without the clinical judgment of a medical or health professional.

OSCON 2012 Healthcare Track — The conjunction of open source and open data with health technology promises to improve creaking infrastructure and give greater control and engagement to patients. Learn more at OSCON 2012, being held July 16-20 in Portland, Oregon.

Save 20% on registration with the code RADAR20

Related:

Older posts are this way If this message doesn't go away, click anywhere on the page to continue loading posts.
Could not load more posts
Maybe Soup is currently being updated? I'll try again automatically in a few seconds...
Just a second, loading more posts...
You've reached the end.

Don't be the product, buy the product!

Schweinderl